U-NetPlus: A Modified Encoder-Decoder U-Net Architecture for Semantic and Instance Segmentation of Surgical Instruments from Laparoscopic Images

With the advent of robot-assisted surgery, there has been a paradigm shift in medical technology for minimally invasive surgery. However, it is very challenging to track the position of the surgical instruments in a surgical scene, and accurate detection & identification of surgical tools is par...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference Ročník 2019; s. 7205 - 7211
Hlavní autoři: Kamrul Hasan, S. M., Linte, Cristian A.
Médium: Konferenční příspěvek Journal Article
Jazyk:angličtina
Vydáno: United States IEEE 01.07.2019
Témata:
Computer architecture
Convolution
Deep Learning
Image Interpretation, Computer-Assisted
Image segmentation
Instruments
Interpolation
Laparoscopy
Robotic Surgical Procedures
Semantics
Surgery
Surgical Instruments
Training
ISSN:2694-0604, 1557-170X, 1558-4615, 2694-0604
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:With the advent of robot-assisted surgery, there has been a paradigm shift in medical technology for minimally invasive surgery. However, it is very challenging to track the position of the surgical instruments in a surgical scene, and accurate detection & identification of surgical tools is paramount. Deep learning-based semantic segmentation in frames of surgery videos has the potential to facilitate this task. In this work, we modify the U-Net architecture by introducing a pre-trained encoder and re-design the decoder part, by replacing the transposed convolution operation with an upsampling operation based on nearest-neighbor (NN) interpolation. To further improve performance, we also employ a very fast and flexible data augmentation technique. We trained the framework on 8 × 225 frame sequences of robotic surgical videos available through the MICCAI 2017 EndoVis Challenge dataset and tested it on 8 × 75 frame and 2 × 300 frame videos. Using our U-NetPlus architecture, we report a 90.20% DICE for binary segmentation, 76.26% DICE for instrument part segmentation, and 46.07% for instrument type (i.e., all instruments) segmentation, outperforming the results of previous techniques implemented and tested on these data.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:2694-0604
1557-170X
1558-4615
2694-0604
DOI:10.1109/EMBC.2019.8856791